Liquid AI Releases Open d1 Decision Models for Edge Inference
Liquid AI has released two open-weight models from its d1 decision model family: d1-3B and the experimental d1-omni-600M. Unlike generative models, these multimodal decision models produce no tokens and answer in a single forward pass. On the Decision Index 0.2.1, d1-3B scores 48.57, ahead of every 4B and 9B model and of Decider 35B-A3B (47.11). d1-3B answers a question in under 10 ms on an RTX 4090 and in under 50 ms on every measured Jetson edge device.
Why it matters
Liquid AI has released two open-weight models from its d1 decision model family: d1-3B and the experimental d1-omni-600M. Unlike generative models, these multimodal decision models produce no tokens and answer in a single forward pass. On the Decision Index 0.2.1, d1-3B scores 48.57, ahead of every 4B and 9B model and of Decider 35B-A3B (47.11). d1-3B answers a question in under 10 ms on an RTX 4090 and in under 50 ms on every measured Jetson edge device.